On the Creation of a Chess-AI-Inspired Problem-Specific Optimizer for the Pseudo Two-Dimensional Battery Model Using Neural Networks

Dawson-Elli, Neal; Kolluri, Suryanarayana; Mitra, Kishalay; Subramanian, Venkat R.

doi:10.1149/2.1261904jes

Cited by 13 publications

(10 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SOC systems are characterized by having access to a large amount of training data that can be collected at small time steps throughout the evolution of the battery, and the neural network performs well on data-rich systems. In addition, a hybrid optimization technique for the P2D battery model inspired by the neural network-based chess engine DeepChess has also been proposed 73 .…”

Section: Selection Of a Machine Learning Approachmentioning

confidence: 99%

Predicting the state of charge and health of batteries using data-driven machine learning

et al. 2020

View full text Add to dashboard Cite

W ith rising concerns about global warming, electrification of transport has recently emerged as an important vision in many countries. The successful development of electric vehicles (EVs) depends highly on the cycling performance, cost and safety of the batteries. Rechargeable lithium-ion (Li-ion) batteries are currently the best choice for EVs due to their reasonable energy density and cycle life 1 . Further research and development on Li-ion batteries will lead to even higher energy density and more complicated battery dynamics, where the efficiency and safety of such batteries will become a concern. An advanced battery management system (BMS) that can monitor and optimize battery behaviour and safety is thus essential for the entire electrification system 2 .Today, one of the major barriers to widespread adoption of EVs is range anxiety. The ability of a BMS to accurately determine the state of charge (SOC) and state of health (SOH) of batteries, and hence the estimated driving range, will alleviate this problem. In addition, reliable prediction of remaining useful life (RUL) will allow batteries to be used to their fullest potential and maximum life expectancy before replacement or disposal. Knowledge of the RUL of spent batteries will also enable their redeployment in less demanding, second-life applications such as stationary grid storage. If we are able to sort manufactured cells based on their expected lifetime using early-cycle data, we can further accelerate the testing, validation and development process of new batteries. In summary, accurate prediction of the current and future state of batteries will open up vast opportunities in battery manufacturing, usage and optimization 3,4 . SOC and SOH are the two most important parameters in battery management and are generally defined as:where C curr is the capacity of the battery in its current state, C full is the capacity of the battery in its fully charged state, C nom is the nominal capacity of the brand-new battery 2 . In essence, SOC denotes the capacity of the battery in its current state compared to the capacity in its fully charged state (equivalent of a fuel gauge), while SOH describes the capacity of the battery in its fully charged state compared to the nominal capacity when brand new. By convention, SOC is 100% when the battery is fully charged and 0% when it is empty, while SOH is 100% at the time of manufacture and reaches 80% at end of life (EOL). In the battery manufacturing industry, EOL is often defined as the point at which the actual capacity at full charge drops to 80% of its nominal value 2 . The remaining number of charge/discharge cycles until the battery reaches EOL is the RUL of the battery. Current BMSs can determine the SOC of Li-ion batteries within 0.6% to 6.5% 5 , but are unable to predict the SOH and RUL of batteries accurately 6 .The traditional methods for SOC estimation include ampere hour counting estimation, open-circuit voltage-based estimation, impedance-based estimation, model-based estimation, fuzzy logic, and Kal...

show abstract

Section: Selection Of a Machine Learning Approachmentioning

confidence: 99%

Predicting the state of charge and health of batteries using data-driven machine learning

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Cell design currently follows a trial-and-error approach and is limited to certain standard formats (i.e., cylindrical, pouch, and prismatic hard-case). However, there are some incipient activities in which modeling is applied to cell design 153,154 , which will open up new opportunities to explore new cell formats and designs.…”

Section: Cell Designmentioning

confidence: 99%

Battery 2030+ Roadmap

Edström¹

2020

View full text Add to dashboard Cite

“…Among all the models, The pseudo-2D (P2D) model has the advantage of accuracy and speed. Therefore, it has been widely used in battery optimization, 2,22,23 data-driven model studies, 24,25 and comprehensive degradation mechanisms studies. 1,2,26 Battery degradation models have been developed to increase the prediction of battery simulation, such as thermal effect, 26,27 mechanical stress, 28 SEI formation, [29][30][31] lithium plating, 8,32,33 lithium stripping, 34,35 electrode volume change, 36 and capacity fade.…”

Section: Plated Lithium-induced Side Reactionsmentioning

confidence: 99%

“…37 In our previous work, a multi-objective optimization framework was developed and applied to study battery design and degradation. 2,22,23,38 These modeling efforts make battery design optimization and optimal control possible. 2,22,23,29,[38][39][40][41][42][43] Numerical investigations on reactions between plated lithium metal and generated water/HF under various conditions are still missing.…”

Section: Plated Lithium-induced Side Reactionsmentioning

confidence: 99%

“…Battery degradation models have been developed to increase the prediction of battery simulation, such as thermal effect, 26,27 mechanical stress, 28 SEI formation, 29‐31 lithium plating, 8,32,33 lithium stripping, 34,35 electrode volume change, 36 and capacity fade 37 . In our previous work, a multi‐objective optimization framework was developed and applied to study battery design and degradation 2,22,23,38 . These modeling efforts make battery design optimization and optimal control possible 2,22,23,29,38‐43 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Toward safe and rapid battery charging: Design optimal fast charging strategies thorough a physics‐based model considering lithium plating

2020

View full text Add to dashboard Cite

Summary The application of lithium‐ion batteries is limited by long charging time and charging‐related degradations. An enhanced fast‐charging strategy can overcome these limitations. This work proposes a novel fast‐charging strategy to charge lithium‐ion batteries safely. This strategy contains a voltage‐spectrum‐based charging current profile that is optimized based on a physics‐based battery model and a genetic algorithm. The battery model considers major degradation events during charging: lithium plating, plated lithium‐induced reactions, SEI growth, as well as other degradations in the electrodes and the electrolyte. Proposed voltage‐spectrum‐based fast charging profiles are investigated with a different resolution of voltage intervals. The results show a charging profile with 15 voltage intervals and an adaptive resolution in the lower voltage range significantly can reduce charging time as well as mitigate battery degradation and avoid lithium plating. Promising results show that the charging time can be reduced without significantly lithium plating, and other side reactions compared to a constant charging strategy.

show abstract

On the Creation of a Chess-AI-Inspired Problem-Specific Optimizer for the Pseudo Two-Dimensional Battery Model Using Neural Networks

Cited by 13 publications

References 30 publications

Predicting the state of charge and health of batteries using data-driven machine learning

Predicting the state of charge and health of batteries using data-driven machine learning

Battery 2030+ Roadmap

Toward safe and rapid battery charging: Design optimal fast charging strategies thorough a physics‐based model considering lithium plating

Contact Info

Product

Resources

About